metadata
license: apache-2.0
base_model: ibm/TTM
tags:
- generated_from_trainer
model-index:
- name: fewshot_5
results: []
fewshot_5
This model is a fine-tuned version of ibm/TTM on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0422
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 512
- eval_batch_size: 512
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2328 | 1.0 | 24 | 0.0388 |
| 0.2256 | 2.0 | 48 | 0.0388 |
| 0.2207 | 3.0 | 72 | 0.0386 |
| 0.2165 | 4.0 | 96 | 0.0386 |
| 0.2132 | 5.0 | 120 | 0.0386 |
| 0.2084 | 6.0 | 144 | 0.0387 |
| 0.2033 | 7.0 | 168 | 0.0392 |
| 0.1971 | 8.0 | 192 | 0.0400 |
| 0.1911 | 9.0 | 216 | 0.0412 |
| 0.1836 | 10.0 | 240 | 0.0422 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1